Product Compare
NVIDIA L40 vs NVIDIA Quadro RTX 8000
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Oct 2022 | Aug 2018 |
| Generation | Tesla Ada | Quadro |
| Type | Professional | Professional |
| Bus Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 735 MHz | 1395 MHz |
| Boost Clock | 2490 MHz | 1770 MHz |
| Memory Clock | 2250 MHz | 1750 MHz |
| Memory | ||
| Memory Size | 48GB | 48GB |
| Memory Type | GDDR6 | GDDR6 |
| Memory Bus | 384bit | 384bit |
| Bandwidth | 864.0GB/s | 672.0GB/s |
| Render Config | ||
| SM Count | 142 | 72 |
| Shading Units | 18176 | 4608 |
| TMUs | 568 | 288 |
| ROPs | 192 | 96 |
| Tensor Cores | 568 | 576 |
| RT Cores | 142 | 72 |
| L1 Cache | 128 KB (per SM) | 64 KB (per SM) |
| L2 Cache | 96 MB | 6 MB |
| Theoretical Performance | ||
| Pixel Rate | 478.1 GPixel/s | 169.9 GPixel/s |
| Texture Rate | 1414 GTexel/s | 509.8 GTexel/s |
| FP16 (half) | 90.52 TFLOPS | 32.62 TFLOPS |
| FP32 (float) | 90.52 TFLOPS | 16.31 TFLOPS |
| FP64 (double) | 1414 GFLOPS | 509.8 GFLOPS |
| Graphics Processor | ||
| GPU Name | AD102 | TU102 |
| GPU Variant | AD102-895-A1 | TU102-875-A1 |
| Architecture | Ada Lovelace | Turing |
| Foundry | TSMC | TSMC |
| Process Size | 4 nm | 12 nm |
| Transistors | 76.3 billion | 18.6 billion |
| Die Size | 608 mm² | 754 mm² |
| Board Design | ||
| TDP | 300W | 260W |
| Suggested PSU | 700 W | 600 W |
| Outputs | 4x DisplayPort 1.4a | 4x DisplayPort 1.4a1x USB Type-C |
| Power Connectors | 1x 16-pin | 1x 6-pin + 1x 8-pin |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 8.9 | 7.5 |
| Shader Model | 6.6 | 6.6 |
| Benchmarks | ||
| Blender | 3901 | 2844 |